Agent llm changed to duckduckgo

app.py

@@ -1,62 +1,54 @@
 import os
-import requests
 import gradio as gr
-from huggingface_hub import login
-from smolagents import CodeAgent
-from smolagents.models import HfApiModel
-from duckduckgo_search import DDGS  # Importiert DuckDuckGo Search
+import requests
+import pandas as pd
+from duckduckgo_search import DDGS
+from smolagents import CodeAgent, Tool
 
-# Tool: DuckDuckGoSearchTool
-class DuckDuckGoTool:
-    def __init__(self):
-        self.name = "DuckDuckGoSearch"
-        self.description = "Tool to search DuckDuckGo for an answer."
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-    def __call__(self, query: str) -> str:
-        """Durchführt eine Suche mit DuckDuckGo und gibt die ersten 3 Ergebnisse zurück."""
-        try:
-            search_results = ddg_search(query)
-            results = [result["title"] + " - " + result["url"] for result in search_results[:3]]
-            return "\n".join(results)
-        except Exception as e:
-            return f"Fehler bei der DuckDuckGo-Suche: {e}"
 
-# Agent: MySmolAgent
-class MySmolAgent:
+# --- DuckDuckGo Search Tool ---
+class DuckDuckGoSearchTool(Tool):
     def __init__(self):
-        print("Initializing SmolAgent...")
-
-        # Sicherstellen, dass der Token korrekt gesetzt ist
-        token = os.getenv("HF_TOKEN")
-        if not token:
-            raise ValueError("HF_TOKEN environment variable is missing.")
+        self.name = "DuckDuckGo Search"
+        self.description = "Searches DuckDuckGo for answers."
+        self.ddgs = DDGS()
 
-        # Anmeldung bei HuggingFace
-        login(token=token)
+    def run(self, inputs: dict) -> str:
+        query = inputs.get("query", "")
+        results = self.ddgs.text(query)
+        if results:
+            return results['abstract']
+        return "No results found."
 
-        # Modell initialisieren
-        self.model = HfApiModel(model="mistralai/Mistral-7B-Instruct-v0.1")
 
-        # Agent mit Tools und Modell einrichten
+# --- Basic Agent Definition ---
+class MySmolAgent:
+    def __init__(self):
+        print("Initializing SmolAgent...")
+        self.search_tool = DuckDuckGoSearchTool()  # The search tool
         self.agent = CodeAgent(
-            tools=[DuckDuckGoTool()],
-            model=self.model,
-            max_steps=5,
+            tools=[self.search_tool],  # Add DuckDuckGoSearchTool to the agent
             name="search_agent",
-            description="Agent that performs web searches using DuckDuckGo."
+            description="Agent that performs web searches using DuckDuckGo.",
+            max_steps=5
         )
 
     def __call__(self, question: str) -> str:
         print(f"Agent running for question: {question[:60]}...")
-        return self.agent.run(question)
+        # Input must be a dictionary where "query" is the search term
+        inputs = {"query": question}
+        return self.agent.run(inputs)
+
 
-# Funktion, um Fragen zu beantworten und die Antworten zu senden
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Holt alle Fragen, lässt den Agenten sie beantworten, sendet alle Antworten,
-    und zeigt die Ergebnisse an.
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
     """
-    # --- Bestimmen der Hugging Face API-URLs ---
+    # --- Determine HF Space Runtime URL and Repo URL ---
     space_id = os.getenv("SPACE_ID")
 
     if profile:
@@ -66,11 +58,11 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print("User not logged in.")
         return "Please Login to Hugging Face with the button.", None
 
-    api_url = "https://agents-course-unit4-scoring.hf.space"
+    api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instanziiere den Agenten
+    # 1. Instantiate Agent (modify this part to create your agent)
     try:
         agent = MySmolAgent()
     except Exception as e:
@@ -80,7 +72,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
-    # 2. Frage abrufen
+    # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -93,14 +85,8 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         return f"Error decoding server response for questions: {e}", None
-    except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
 
-    # 3. Agent ausführen
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -115,19 +101,19 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            print(f"Error running agent on task {task_id}: {e}")
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Bereite Submission vor
+    # 4. Prepare Submission 
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
 
-    # 5. Einreichung
+    # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -143,18 +129,35 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
+    except requests.exceptions.HTTPError as e:
+        error_detail = f"Server responded with status {e.response.status_code}."
+        try:
+            error_json = e.response.json()
+            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
+        except requests.exceptions.JSONDecodeError:
+            error_detail += f" Response: {e.response.text[:500]}"
+        status_message = f"Submission Failed: {error_detail}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.Timeout:
+        status_message = "Submission Failed: The request timed out."
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
     except requests.exceptions.RequestException as e:
-        error_detail = f"Submission Failed: Network error - {e}"
-        print(error_detail)
+        status_message = f"Submission Failed: Network error - {e}"
+        print(status_message)
         results_df = pd.DataFrame(results_log)
-        return error_detail, results_df
+        return status_message, results_df
     except Exception as e:
         status_message = f"An unexpected error occurred during submission: {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
-# Gradio-Interface
+
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
@@ -175,6 +178,7 @@ with gr.Blocks() as demo:
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -183,5 +187,4 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True)